© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104292
    Prev
    Next
    INDEX
    Explanations

    code and scripting constructs

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron responds to numeric tokens (e.g. numbers, numeric constants) in formulas or code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sertation
    -0.91
    OOTDTY
    -0.91
    ctivo
    -0.91
    folie
    -0.90
    bildet
    -0.90
     andet
    -0.87
    maske
    -0.86
     дуб
    -0.86
    ριά
    -0.84
    achting
    -0.84
    POSITIVE LOGITS
    খ
    0.91
     Suffering
    0.84
     estoque
    0.82
    burning
    0.81
     Luxe
    0.80
     trenger
    0.79
     partnered
    0.78
    வர
    0.78
    пература
    0.77
     Allahabad
    0.77
    Activations Density 0.001%

    No Known Activations